dcr-v1-to-v2

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow performs V1 discovery by calling SAMOOHA introspection procedures (e.g., provider.view_cleanrooms, provider.view_provider_datasets, provider.view_join_policy, provider.view_added_templates) and then retrieves template bodies from the clean room app package tables (SAMOOHA_CLEANROOM_APP_<CLEANROOM_NAME>.*.CUSTOM_SQL_TEMPLATES), which are outsider-authored free text (templates/definitions created by other parties) that the agent ingests into LLM context for conversion and file generation.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)